environment-mcp
MCP server that provides tools to access Google Maps Environment APIs for air quality, pollen, and weather data, enabling queries like current conditions, forecasts, and history.
README
environment-mcp
MCP (Model Context Protocol) server that proxies Google Maps Platform Environment APIs: Air Quality, Pollen, and Weather. Uses stdio transport and a single API key from the environment.
Prerequisites
- Node.js 20+
- A Google Cloud project with billing enabled
- APIs enabled: Air Quality API, Pollen API, Weather API (APIs & Services → Library)
- An API key (APIs & Services → Credentials), with usage restricted appropriately for your setup
See the product setup guides for details: Air Quality, Pollen, Weather.
Install and run
npm install
npm run build
Set the key (do not commit it):
export GOOGLE_MAPS_API_KEY="your-key"
Alternatively use GOOGLE_ENVIRONMENT_API_KEY.
Start the server (stdio; typically launched by an MCP client, not used interactively):
npm start
For development with auto-reload:
npm run dev
Cursor MCP configuration
After npm run build, add a server entry (adjust the path to your clone):
{
"mcpServers": {
"google-environment": {
"command": "node",
"args": ["/absolute/path/to/environment-mcp/dist/index.js"],
"env": {
"GOOGLE_MAPS_API_KEY": "your-key-here"
}
}
}
}
You can omit env if GOOGLE_MAPS_API_KEY is already set in your shell profile and Cursor inherits it (behavior depends on how Cursor is launched).
Tools
| Tool | API |
|---|---|
air_quality_current_conditions |
POST .../v1/currentConditions:lookup |
air_quality_forecast |
POST .../v1/forecast:lookup |
air_quality_history |
POST .../v1/history:lookup |
pollen_forecast |
GET .../v1/forecast:lookup |
weather_current_conditions |
GET .../v1/currentConditions:lookup |
weather_forecast_days |
GET .../v1/forecast/days:lookup |
weather_forecast_hours |
GET .../v1/forecast/hours:lookup |
weather_history_hours |
GET .../v1/history/hours:lookup |
weather_public_alerts |
GET .../v1/publicAlerts:lookup |
Air quality tools accept a JSON body with required location: { latitude, longitude } and optional fields per Google’s REST reference; other tools use typed arguments (coordinates, days, hours, unitsSystem, etc.).
Linting
Uses Ultracite (Biome preset):
npm run lint
npm run format
Security
- Never pass the API key in tool arguments; only use environment variables.
- Restrict the key in Google Cloud Console (HTTP referrers for browser use; IP or server-only patterns for backend).
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.